GenAI Algorithms Intern – Model Optimization for Inference
Switzerland, Zurich • Internship
Posted 26d ago
Job Location
Switzerland, Zurich
Tech Stack
Remote Work Policy
On-site
Employment Type
Internship
Categories
AI Engineer
About the job
NVIDIA is seeking a GenAI Algorithms Intern to optimize state-of-the-art generative AI models, including LLMs, VLMs, and diffusion models, for maximal inference efficiency. This role involves designing, implementing, and productionizing model optimization algorithms for deployment on NVIDIA's latest hardware. The focus is on ease of use, compute and memory efficiency, and achieving optimal accuracy-performance trade-offs through software-hardware co-design. The work spans multiple layers of the AI software stack, from algorithm design to integration within NVIDIA's ecosystem and open-source frameworks, with potential for GPU-level optimization including custom kernel development.
Responsibilities
- Design and build modular, scalable model optimization software platforms.
- Explore, develop, and integrate deep learning optimization algorithms (quantization, speculative decoding, sparsity, distillation, pruning, neural architecture search).
- Deploy optimized models into open-source inference frameworks and contribute specialized APIs and features.
- Collaborate with NVIDIA teams on model optimization solutions for customer use cases.
- Conduct GPU kernel-level profiling to identify and capitalize on hardware and software optimization opportunities.
Requirements
- Pursuing a Master's or PhD in Computer Science, AI, Applied Math, or a related field.
- Strong deep learning background and hands-on experience with language models.
- Solid foundation in algorithms and programming.
- Proficiency in Python, PyTorch, and modern ML frameworks/tools.
- Good written and verbal communication skills.
- Ability to work both independently and collaboratively in a fast-paced environment.
Benefits
- Highly competitive salaries
- Comprehensive benefits package
